Testing Without Test Code: AI-Driven QA on Mobile Apps
What happens when an AI agent reads a scenario document and executes it on a real iOS simulator — adapting to layout shifts, verifying with screenshots, and writing the report itself.
Engineering Insights.
What we've learned shipping production systems. AI, architecture, and 25 years of pattern recognition.
Who's reviewing your AI-generated code?
Your team ships 5x the code. Who's checking it? AI-generated code has specific failure modes that junior engineers can't catch. Here's the honest picture.
Agentic AI in Production: What Actually Works
After building agentic AI systems in production environments, here's the honest accounting of what works, what fails, and what the hype gets wrong. From Eloquentix engineers.
MCP Security for Enterprise
Model Context Protocol connects your AI to live business data. Before you deploy: prompt injection, tool poisoning, over-permissioning, and a four-pillar security framework from Eloquentix engineers.
Real-Time at Scale: Architecture Lessons from E.ON's Virtual Power Plant
12 years building E.ON's Virtual Power Plant — dispatching 400 assets simultaneously across four countries. What the architecture looks like, what failed, and what it teaches about real-time systems at TSO grade.
Google Apps Script Is a Hidden AI Gem
While talking to someone who is among the most forward implementors of AI solutions in the enterprise, we both agreed that where agents are deployed is...
Introducing Kardia: What an AI Constitution Should Be
We just published Kardia, our take on what an AI constitution should be. kardia.eloquentix.com
AI Burnout, Right on Cue
In mid-February, after coming back from China and catching up with AI, a partner told me about all the agents he had set up, the scaffolding, the...
Agents Require a Text Abstraction Layer of Your Thinking
The divergence between those who are still on GPT's creepy voice and those running agents of different sorts is widening, and it may be that it is not...
RandomMaxxing: Staying Human in a Computer-Driven World
May I kindly ask to share a new term: RandomMaxxing.
Claude Mythos: Six Ways an Aligned Model Quietly Misbehaves
Some of Claude Mythos' adventures (credit @hesamation). This is exactly why a constitution built on formation, not just constraint, matters:
What's Resilient in an AI World? Maybe Character
Many who are aware of AI capabilities today are scared of their future. What is resilient in an AI world? Skills? Judgement? Rolodex? Knowledge? All...
Software Abundance and the Age of Abundance
You may have heard various tech voices say that we are headed to an age of abundance. This idea may seem cuckoo, but it is worth understanding where it...
Jony Ive, Steve Jobs, and the Psychopathy of Corporate Mediocrity
I saw a post on X about an interaction between Jony Ive and Steve Jobs that stuck with me. Asking the models what they think landed on remarkable...
Apple's Real Strategy: Devices as Data Aggregators for an Experience
I was listening to the original iPod presentation from 2001, the '1000 songs in your pocket' one. Actually the most important part was at the beginning.
Our Brains Are Learning to Forget Like Feeds
Our brain's capacity to forget is adapting to feeds. Just like you don't remember the details of the asphalt and trees that you saw in the last 24...
A Moral Question About AI: Should It Be Any Different?
Most people have never heard of ZF. This German company quietly builds the world's best automatic transmissions. Their 8-speed ZF 8HP powers BMWs,...
The Paradigm Shift: From ML Observation to GenAI Manipulation
After a few days taking to a young researcher at Wisconsin, he said that our discussions highlighted to him the difference between ML and what we now...
Karpathy's Autoresearch
Singularity stuff. Karpathy just addressed the priciest bottleneck in ML research for free. Researcher iteration speed. A senior ML engineer bleeds...
Metals LSP Plugin for Claude Code
Our latest open-source contribution at Eloquentix: the Metals LSP plugin for Claude Code. This integration brings advanced Scala language server...
AI Workload Creep
If it was not obvious.
Coding Agents Changed in December
Here is what Karpathy is saying and it hard to disagree after using tools in February 26. And these again are the worse tools we will ever have.
Google's Universal Commerce Protocol
Google just released the Universal Commerce Protocol -- an open-source standard for AI-powered shopping.
How Claude Would Code Without Humans
We asked Claude what it thought about human code and how it would approach coding if humans were not in the loop. Here is a part of its answer.
With AI, All Codebases Are Legacy
From an Eloquentix developer:
Co-workers Are Non-Deterministic
Co-workers are non-deterministic. That is why we have audits.
Innovation Gets the Glory
There's a pattern in how nations lose economic dominance that we keep missing. Europe gave us quantum mechanics, radioactivity, and modern chemistry....
Claude Code: Why It Feels Like Playing a Video Game
About Claude Code: The best compliment one can give to it is that it feels like playing a video game.
AI Got Developers to Pay for Software
AI has done something no human ever could.
Every AI Model Has a Cultural Personality
All the big labs pretrain on the ~same internet, but each has a secret sauce:
Formula SAE: Where Engineering Meets Entrepreneurship
Congrats PER.
The UX for Long-Running AI Agents
"The UX for long running AI Agents is going to be one of the most interesting design questions in the coming years. The more the agent is doing complex...
Virtual Power Plants and Grid Stability
Having worked on the best VPP in Europe for the last 10 years, what Spain's massive blackout, exposed the risks of relying heavily on renewables...
GPT-4.1 Agentic Workflows: Practical Tips
GPT-4.1 is out and here are some tips from inside OpenAI.
UX Principles for Agentic AI Systems
Emerging UX principles for agentic AI -- systems that act autonomously to achieve goals -- focus on balancing user control, trust, and seamless...
Shopify's AI-First Memo
With full appreciation of the clarity of his prose, here is Tobi Lutke's message to Shopify.
Prompt Engineering Is Micromanagement
"radu, nobody understands your posts, so say whatever" here you go:
The Age of Vibe Coding
Garry Tan - yCombinator:
Testing AI Models: Roman Game Benchmark
Grok3 Think mode is impressive. Since ChatGPT came out 27 months ago, at every model release I have tested it with my own test, a roman game that 1) Is...
Cursor's $700M Valuation
These Cursor mfs forked VSCode, added anthropic keys & a chat window, and now are worth ~$700mm EACH at 25 years old.
Apple iCloud at Scale
Listening to AAPL earning, I heard that their services revenue is running at 105b/year with a 14% growth rate. Double clicking on that, they have over...
AI Agents Are the New Microservices
AI Agents & Microservices: A New Paradigm for Dev Teams
Transformers and DNA
With GPT-4b micro, OpenAI shows that transformers are perfectly suited for protein engineering. Think about it - transformers process sequences of...
DeepSeek V3: How They Trained a Frontier Model Efficiently
Summary of how DeepSeek V3 was so efficient at training a frontier-level model according to Perplexity:
Jensen Huang's 60 Direct Reports
Minimizing layers in an organization is empowering. It treats others like adults. This is rare especially outside the United States.